Block chain-based micro-grid power dispatching method and system, medium and equipment

Abstract

The invention provides a micro-grid power dispatching method and system based on a block chain, a medium and equipment, and relates to the technical field of power regulation and control, and the method comprises the steps: collecting related data in a micro-grid in real time, and uploading the related data to a block chain network, the related data comprising power data, equipment state data and user demand data; processing and analyzing the power data, the equipment state data and the user demand data to obtain an analysis result to generate a power dispatching basis; formulating a power dispatching strategy according to the power dispatching basis; verifying the identity information of the power user and the data authenticity of the power equipment; formulating an excitation strategy according to the power consumption behavior of the power consumer and the operation condition of the power equipment; the consensus of the power dispatching data is realized through the block chain network, and the efficiency and accuracy of power dispatching are improved.

Description

Technical Field

[0001] The present invention relates to the field of power control technology, and in particular to a microgrid power dispatching method, system, medium and equipment based on blockchain. Background Art

[0002] With the rapid development of renewable energy, microgrids, as a new type of energy system, are gaining more and more attention. Microgrids are small power systems composed of distributed power sources, loads, energy storage devices and power electronic equipment, and have the characteristics of autonomy, flexibility, reliability and environmental protection. Microgrids can achieve efficient use of renewable energy, improve the power supply quality and reliability of the power system, and reduce energy consumption and environmental pollution.

[0003] However, the power dispatch and control of microgrids still face some challenges. Traditional power dispatch systems usually rely on a central control center, all decisions need to be processed centrally, data needs to be transmitted between the control center and distributed energy resources (DERs), and delays in communication links may lead to slow dispatch responses. Traditional dispatch decisions may involve approval and coordination at multiple levels, which increases decision-making time. And traditional dispatch methods may lack advanced optimization algorithms and cannot achieve efficient utilization of a large number of distributed energy resources and energy storage devices. Dispatch systems that rely on manual operations are often inefficient and prone to errors and omissions. Traditional dispatch systems may not be able to quickly adapt to dynamic changes in microgrids, such as load fluctuations and the intermittent nature of renewable energy. Data storage in centralized systems may be vulnerable to hacker attacks, resulting in data leakage or tampering.

[0004] Traditional power dispatching has problems such as slow dispatching speed, low efficiency, and poor data security. In addition, due to the large number of distributed power sources and energy storage devices in microgrids, traditional dispatching methods are difficult to achieve efficient and accurate control of them. Summary of the invention

[0005] In order to overcome the shortcomings of the above-mentioned prior art such as slow power dispatching speed, low efficiency, and poor data security, the main purpose of the present invention is to provide a microgrid power dispatching method, system, medium and equipment based on blockchain.

[0006] To achieve the above objectives, the present invention adopts the following technical solutions, a microgrid power dispatching method based on blockchain, including:

[0007] Collect relevant data in the microgrid in real time and upload it to the blockchain network after preprocessing. The relevant data includes power resource data, equipment status data, and user demand data;

[0008] Obtain historical power data and build a power resource prediction model through time series analysis; obtain equipment operating parameters and build an equipment load model through deep learning; obtain historical power consumption data and build a power demand model through machine learning;

[0009] Inputting relevant data into the power resource prediction model, the equipment load model, and the power demand model respectively, to obtain power resource prediction data, equipment load prediction data, and power demand prediction data respectively;

[0010] Extract the data features of historical power data, equipment operating parameters, and historical power consumption data, obtain the features related to power transmission efficiency based on correlation analysis, and determine their respective weights based on principal component analysis;

[0011] Taking maximizing efficiency as the objective function, an efficiency transmission model is constructed according to the weights of historical power data, equipment operating parameters and historical power consumption data, and optimized through simulated annealing and taboo search to obtain the optimized efficiency transmission model;

[0012] The power resource forecast data, equipment load forecast data, and power demand forecast data are input into the optimized efficiency transmission model to obtain the power transmission result with maximum efficiency, and then obtain the power dispatch plan with maximum efficiency.

[0013] The method of obtaining historical power data and constructing a power resource prediction model through time series analysis includes the following steps:

[0014] Acquire historical power data and pre-process it, including power resource data and power load data;

[0015] Extract features from historical power data to obtain multiple features, including time features, power resource features, power load features, and environmental features;

[0016] Based on time series analysis, a power resource prediction model is constructed, and the power resource prediction model is optimized by a random forest algorithm to obtain an optimized power resource prediction model. The device operation parameters are obtained and the device load model is constructed by deep learning, including the following steps:

[0017] Acquire equipment operating parameters and perform preprocessing to obtain preprocessed equipment operating parameters; perform feature extraction on the preprocessed equipment operating parameters, and obtain parameter features whose correlation with equipment load is greater than a set range through screening;

[0018] And build equipment load model through recurrent neural network;

[0019] The preprocessed equipment operating parameters are used to train and verify the equipment load model to obtain a trained equipment load model.

[0020] The method of obtaining historical electricity consumption data and constructing an electricity demand model through machine learning includes the following steps:

[0021] Obtain historical electricity consumption data and pre-process it;

[0022] Perform feature engineering on historical electricity consumption data, extract features related to electricity demand, and perform normalization and standardization to obtain processed feature data;

[0023] The processed feature data is used as input to build the power demand model through support vector machine.

[0024] The efficiency transmission model is constructed by taking the maximum efficiency as the objective function and according to the weights of the historical power data, the equipment operation parameters and the historical power consumption data, and includes the following steps:

[0025] Determine the objective function to maximize efficiency, including maximizing the total power supply efficiency of the power system;

[0026] According to the power resource forecasting model, the equipment load model and the power demand model, the corresponding constraints are determined to be the supply limit of power resources, the operation limit of equipment load and the satisfaction requirement of power demand;

[0027] According to the objective function and multiple constraints, the efficiency delivery model is constructed through linear regression, combining the weights of historical power data, equipment operating parameters and historical power consumption data.

[0028] The power resource forecast data, equipment load forecast data, and power demand forecast data are input into the optimized efficiency transmission model to obtain the power transmission result with the maximum efficiency, and then obtain the power dispatching plan with the maximum efficiency, including the following steps:

[0029] Extract features from the forecast data of power resources, equipment loads, and power demand to obtain forecast features;

[0030] The prediction features related to power transmission efficiency are obtained through correlation analysis. The prediction features are combined with the weights of historical power data, equipment operating parameters and historical power consumption data, and then input into the efficiency transmission model after data fusion, to achieve the power transmission result with the maximum efficiency.

[0031] Based on the results of maximized power transmission efficiency, formulate a power dispatch plan with maximized efficiency.

[0032] The microgrid power dispatching system based on blockchain includes:

[0033] The data acquisition module is used to collect relevant data in the microgrid in real time and upload it to the blockchain network after preprocessing. The relevant data includes power resource data, equipment status data, and user demand data;

[0034] The data analysis module is used to obtain historical power data and build a power resource prediction model through time series analysis; obtain equipment operating parameters and build an equipment load model through deep learning; obtain historical power consumption data and build a power demand model through machine learning; input relevant data into the power resource prediction model, equipment load model, and power demand model respectively to obtain power resource prediction data, equipment load prediction data, and power demand prediction data respectively;

[0035] The data processing module is used to extract the data features of historical power data, equipment operating parameters and historical power consumption data, and obtain the features related to power transmission efficiency based on correlation analysis, and determine the respective weights based on principal component analysis; taking maximizing efficiency as the objective function, constructing an efficiency transmission model based on the weights of historical power data, equipment operating parameters and historical power consumption data, and optimizing it through simulated annealing and taboo search to obtain the optimized efficiency transmission model;

[0036] The scheme processing module is used to input the power resource forecast data, equipment load forecast data, and power demand forecast data into the optimized efficiency transmission model to obtain the power transmission result with maximum efficiency, and then obtain the power dispatch scheme with maximum efficiency.

[0037] A computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the following steps are performed:

[0038] Collect relevant data in the microgrid in real time and upload it to the blockchain network after preprocessing. The relevant data includes power resource data, equipment status data, and user demand data;

[0039] Obtain historical power data and build a power resource prediction model through time series analysis; obtain equipment operating parameters and build an equipment load model through deep learning; obtain historical power consumption data and build a power demand model through machine learning;

[0040] Inputting relevant data into the power resource prediction model, the equipment load model, and the power demand model respectively, to obtain power resource prediction data, equipment load prediction data, and power demand prediction data respectively;

[0041] Extract the data features of historical power data, equipment operating parameters, and historical power consumption data, obtain the features related to power transmission efficiency based on correlation analysis, and determine their respective weights based on principal component analysis;

[0042] Taking maximizing efficiency as the objective function, an efficiency transmission model is constructed according to the weights of historical power data, equipment operating parameters and historical power consumption data, and optimized through simulated annealing and taboo search to obtain the optimized efficiency transmission model;

[0043] The power resource forecast data, equipment load forecast data, and power demand forecast data are input into the optimized efficiency transmission model to obtain the power transmission result with maximum efficiency, and then obtain the power dispatch plan with maximum efficiency.

[0044] A computer device comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the following steps are performed:

[0045] Collect relevant data in the microgrid in real time and upload it to the blockchain network after preprocessing. The relevant data includes power resource data, equipment status data, and user demand data;

[0046] Obtain historical power data and build a power resource prediction model through time series analysis; obtain equipment operating parameters and build an equipment load model through deep learning; obtain historical power consumption data and build a power demand model through machine learning;

[0047] Inputting relevant data into the power resource prediction model, the equipment load model, and the power demand model respectively, to obtain power resource prediction data, equipment load prediction data, and power demand prediction data respectively;

[0048] Extract the data features of historical power data, equipment operating parameters, and historical power consumption data, obtain the features related to power transmission efficiency based on correlation analysis, and determine their respective weights based on principal component analysis;

[0049] Taking maximizing efficiency as the objective function, an efficiency transmission model is constructed according to the weights of historical power data, equipment operating parameters and historical power consumption data, and optimized through simulated annealing and taboo search to obtain the optimized efficiency transmission model;

[0050] The power resource forecast data, equipment load forecast data, and power demand forecast data are input into the optimized efficiency transmission model to obtain the power transmission result with maximum efficiency, and then obtain the power dispatch plan with maximum efficiency.

[0051] Compared with the prior art, the beneficial effects of the present invention are:

[0052] 1. Improved data security and transparency. By uploading the data collected in the microgrid to the blockchain network, this method ensures that the data cannot be tampered with and is traceable. The distributed ledger technology of the blockchain can provide a transparent and secure data sharing environment. All participants (including electricity suppliers, consumers, and regulators) can access the data, but cannot unilaterally modify the recorded information. This improvement in transparency and security helps to enhance the trust of the system, reduce fraud, and promote cooperation and innovation.

[0053] 2. Optimal allocation of power resources. By constructing a power resource prediction model, equipment load model, and power demand model, this method can achieve dynamic adjustment and optimal allocation of power resources. By analyzing historical and real-time data, the system can predict changes in power generation and demand, thereby optimizing power allocation strategies and reducing waste while ensuring that consumer demand is met. This is especially important in environments where resources are limited or costs are high.

[0054] 3. Improved equipment operation efficiency: The equipment load model built through deep learning can effectively predict the equipment's operating status and maintenance requirements, thereby achieving real-time monitoring and optimization of equipment operating parameters. This helps to identify potential equipment failures in advance, reduce unexpected downtime, extend equipment life, and reduce maintenance costs.

[0055] 4. Accurate prediction and response to electricity demand. The electricity demand model built using machine learning technology can accurately predict the electricity usage patterns of different user groups. This accurate demand forecast makes power dispatch more flexible and efficient, helps to balance the power load during peak demand periods, and reduces the pressure of peak demand on the power grid.

[0056] 5. Comprehensive optimization and intelligent dispatching, through simulated annealing and taboo search optimization algorithms, combined with multiple data models and prediction results, this method can achieve comprehensive optimization of power dispatching. This not only improves the overall efficiency of the power system, but also dynamically adjusts strategies according to real-time data to respond to emergencies or changes in demand, ensuring the stability and reliability of power supply.

[0057] In short, the operation efficiency, reliability and economy of microgrids are improved. At the same time, the transparency and credibility of the dispatching process are enhanced, and user participation is improved, which helps promote the development and use of sustainable energy. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] The drawings described herein are used to provide further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute improper limitations on the present application.

[0059] Figure 1It is a schematic diagram of the process structure of the present invention;

[0060] Figure 2 It is a schematic diagram of the system module of the present invention;

[0061] Figure 3 It is a schematic diagram of some modules of the present invention;

[0062] Figure 4 It is a schematic diagram of the process module structure of the present invention. DETAILED DESCRIPTION

[0063] The present invention will be further described below in conjunction with the accompanying drawings and implementation modes.

[0064] Example 1

[0065] See also Figure 1 - Figure 4 , a microgrid power dispatching method based on blockchain, including the following steps: real-time collection of relevant data in the microgrid, and uploading to the blockchain network after preprocessing, wherein the relevant data includes power resource data, equipment status data and user demand data; data collection: installing smart sensors and meters in the microgrid to collect data on power generation, load consumption, equipment operating status and user demand in real time. The data is cleaned and formatted before uploading, and the data is encrypted to protect user privacy and data security. Blockchain technology is used to ensure the immutability and transparency of data. Each data block is recorded on the chain, and all transactions require network consensus. Obtain historical power data, and build a power resource prediction model through time series analysis; obtain equipment operating parameters, and build an equipment load model through deep learning; obtain historical power consumption data, and build a power demand model through machine learning; input the relevant data into the power resource prediction model, the equipment load model, and the power demand model, respectively, to obtain power resource prediction data, equipment load prediction data, and power demand prediction data;

[0066] Extract the data features of historical power data, equipment operating parameters, and historical power consumption data, and obtain features related to power transmission efficiency, such as peak load period, conventional equipment power consumption, etc., based on correlation analysis, and determine the weight of each feature based on principal component analysis;

[0067] Taking maximizing efficiency as the objective function, the predicted data and various weights are integrated. That is, the efficiency transmission model is constructed based on the weights of historical power data, equipment operating parameters and historical power consumption data. The optimized efficiency transmission model is obtained through simulated annealing and taboo search.

[0068] The power resource forecast data, equipment load forecast data, and power demand forecast data are input into the optimized efficiency transmission model to obtain the power transmission result with maximum efficiency, and then obtain the power dispatch plan with maximum efficiency. The dispatch plan should include power flow, load adjustment and demand response strategy.

[0069] Obtain historical power data and build a power resource forecasting model through time series analysis, including the following steps:

[0070] Acquire historical power data and pre-process it, including power resource data and power load data;

[0071] Extract features from historical power data to obtain multiple features, including time features, power resource features, power load features, and environmental features;

[0072] Based on time series analysis, an electric power resource prediction model is constructed, and the electric power resource prediction model is optimized through the random forest algorithm to obtain the optimized electric power resource prediction model.

[0073] The method of obtaining equipment operating parameters and constructing an equipment load model through deep learning includes the following steps:

[0074] Acquire equipment operating parameters and perform preprocessing to obtain the preprocessed equipment operating parameters;

[0075] Extract the characteristics of the pre-processed equipment operating parameters, and obtain the parameter characteristics whose correlation with the equipment load is greater than the set range through screening;

[0076] And build equipment load model through recurrent neural network;

[0077] The preprocessed equipment operating parameters are used to train and verify the equipment load model to obtain a trained equipment load model.

[0078] The method of obtaining historical electricity consumption data and constructing an electricity demand model through machine learning includes the following steps:

[0079] Obtain historical electricity consumption data and pre-process it;

[0080] Perform feature engineering on historical electricity consumption data, extract features related to electricity demand, and perform normalization and standardization to obtain processed feature data;

[0081] The processed feature data is used as input to build the power demand model through support vector machine.

[0082] The efficiency transmission model is constructed by taking the maximum efficiency as the objective function and according to the weights of the historical power data, the equipment operation parameters and the historical power consumption data, and includes the following steps:

[0083] Determine the objective function to maximize efficiency, including maximizing the total power supply efficiency of the power system;

[0084] According to the power resource forecasting model, the equipment load model and the power demand model, the corresponding constraints are determined to be the supply limit of power resources, the operation limit of equipment load and the satisfaction requirement of power demand;

[0085] According to the objective function and multiple constraints, the efficiency delivery model is constructed through linear regression, combining the weights of historical power data, equipment operating parameters and historical power consumption data.

[0086] The power resource forecast data, equipment load forecast data, and power demand forecast data are input into the optimized efficiency transmission model to obtain the power transmission result with the maximum efficiency, and then obtain the power dispatching plan with the maximum efficiency, including the following steps:

[0087] Extract features from the forecast data of power resources, equipment loads, and power demand to obtain forecast features;

[0088] The prediction features related to power transmission efficiency are obtained through correlation analysis. The prediction features are combined with the weights of historical power data, equipment operating parameters and historical power consumption data, and then input into the efficiency transmission model after data fusion, to achieve the power transmission result with the maximum efficiency.

[0089] Based on the results of maximized power transmission efficiency, formulate a power dispatch plan with maximized efficiency.

[0090] Example 2

[0091] Based on the blockchain microgrid power dispatching method in Example 1, a specific implementation case can be designed to illustrate the application of the method. Assume that there is a small microgrid that serves a small community, which includes residential users, commercial buildings and a small factory. The following are the detailed steps and description of the implementation case:

[0092] Smart sensors and metering devices are installed in the microgrid to collect real-time data including power resource data, such as solar panels and wind power generation, power consumption, that is, user demand data, equipment status data, such as energy storage systems and transformers, and user demand data obtained through smart meters.

[0093] The collected data is preprocessed as necessary, such as data cleaning and normalization, and then the processed data is uploaded to the blockchain network through a secure network connection. The data upload uses blockchain encryption and distributed ledger technology to ensure the security and integrity of the data.

[0094] Based on historical power resource data, use time series analysis (such as ARIMA model) to build daily, weekly, and monthly power resource output forecasting models. Use deep learning technology (such as long short-term memory network LSTM) to analyze equipment operating parameters, build equipment load forecasting models, and predict the power consumption of each device. Use machine learning algorithms (such as random forest or neural network) to analyze historical power consumption data, build power demand models, and predict users' power demand patterns.

[0095] Extract features such as mean, variance, correlation, etc. from historical power data, equipment operating parameters, and power consumption data. Analyze the correlation between these features to find out the features related to power transmission efficiency.

[0096] The objective function is to maximize the efficiency of power transmission. Combined with the feature weights of historical data, an efficiency transmission model is constructed, taking into account the forecast data of power resources, equipment load and power demand.

[0097] Heuristic algorithms such as simulated annealing and taboo search are used to optimize the efficiency transmission model, and the best power distribution strategy is obtained by seeking the optimal solution to adapt to the real-time changing power demand and supply situation.

[0098] The predicted power resources, equipment load and power demand data are input into the optimized efficiency transmission model. According to the model calculation, the power dispatch plan with maximum efficiency is obtained, including energy distribution, equipment operation optimization and user demand satisfaction.

[0099] Automatically or manually execute power dispatch plans to adjust the allocation of power resources based on forecasts and real-time data, such as adjusting the charging and discharging of energy storage equipment, optimizing the use of renewable energy, and adjusting demand-side response measures.

[0100] Verify the efficiency and effectiveness of the scheduling plan by continuously monitoring the implementation effect and system operation status. Dynamically adjust the scheduling plan based on actual operation data and new forecast information to cope with possible equipment failures, sudden weather changes or unforeseen demand fluctuations.

[0101] It should be noted that, in the present invention, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprises" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or includes elements inherent to such process, method, article or device.

[0102] The above embodiments are merely examples of the present invention and do not limit the protection scope of the present invention. All designs that are the same or similar to the present invention fall within the protection scope of the present invention.

Claims

1. A microgrid power dispatching method based on blockchain, characterized in that: The following steps are involved: Collect relevant data in the microgrid in real time and upload it to the blockchain network after preprocessing. The relevant data includes power resource data, equipment status data, and user demand data; Obtain historical power data and build a power resource prediction model through time series analysis; obtain equipment operating parameters and build an equipment load model through deep learning; obtain historical power consumption data and build a power demand model through machine learning; Inputting relevant data into the power resource prediction model, the equipment load model, and the power demand model respectively, to obtain power resource prediction data, equipment load prediction data, and power demand prediction data respectively; Extract the data features of historical power data, equipment operating parameters, and historical power consumption data, obtain the features related to power transmission efficiency based on correlation analysis, and determine their respective weights based on principal component analysis; Taking maximizing efficiency as the objective function, an efficiency transmission model is constructed according to the weights of historical power data, equipment operating parameters and historical power consumption data, and optimized through simulated annealing and taboo search to obtain the optimized efficiency transmission model; The power resource forecast data, equipment load forecast data, and power demand forecast data are input into the optimized efficiency transmission model to obtain the power transmission result with maximized efficiency, and then obtain the power dispatch method with maximized efficiency.

2. The microgrid power dispatching method based on blockchain as claimed in claim 1, characterized in that: The method of obtaining historical power data and constructing a power resource prediction model through time series analysis includes the following steps: Acquire historical power data and pre-process it, including power resource data and power load data; Extract features from historical power data to obtain multiple features, including time features, power resource features, power load features, and environmental features; Based on time series analysis, an electric power resource prediction model is constructed, and the electric power resource prediction model is optimized through the random forest algorithm to obtain the optimized electric power resource prediction model.

3. The microgrid power dispatching method based on blockchain as claimed in claim 1, characterized in that: The method of obtaining equipment operating parameters and constructing an equipment load model through deep learning includes the following steps: Acquire equipment operating parameters and perform preprocessing to obtain the preprocessed equipment operating parameters; Extract the characteristics of the pre-processed equipment operating parameters, and obtain the parameter characteristics whose correlation with the equipment load is greater than the set range through screening; And build equipment load model through recurrent neural network; The equipment load model is trained and verified using the preprocessed equipment operating parameters to obtain a trained equipment load model.

4. The microgrid power dispatching method based on blockchain as claimed in claim 1, characterized in that: The method of obtaining historical electricity consumption data and constructing an electricity demand model through machine learning includes the following steps: Obtain historical electricity consumption data and pre-process it; Perform feature engineering on historical electricity consumption data, extract features related to electricity demand, and perform normalization and standardization to obtain processed feature data; The processed feature data is used as input to build the power demand model through support vector machine.

5. The microgrid power dispatching method based on blockchain as claimed in claim 1, characterized in that: The efficiency transmission model is constructed by taking the maximum efficiency as the objective function and according to the weights of the historical power data, the equipment operation parameters and the historical power consumption data, and includes the following steps: Determine the objective function to maximize efficiency, including maximizing the total power supply efficiency of the power system; According to the power resource forecasting model, the equipment load model and the power demand model, the corresponding constraints are determined to be the supply limit of power resources, the operation limit of equipment load and the satisfaction requirement of power demand; According to the objective function and multiple constraints, the efficiency delivery model is constructed through linear regression, combining the weights of historical power data, equipment operating parameters and historical power consumption data.

6. The microgrid power dispatching method based on blockchain as claimed in claim 1, characterized in that: The power resource forecast data, equipment load forecast data, and power demand forecast data are input into the optimized efficiency transmission model to obtain the power transmission result with the maximum efficiency, and then obtain the power dispatching plan with the maximum efficiency, including the following steps: Extract features from the forecast data of power resources, equipment loads, and power demand to obtain forecast features; The prediction features related to power transmission efficiency are obtained through correlation analysis. The prediction features are combined with the weights of historical power data, equipment operating parameters and historical power consumption data, and then input into the efficiency transmission model after data fusion, to achieve the power transmission result with the maximum efficiency. Based on the results of maximized power transmission efficiency, formulate a power dispatch plan with maximized efficiency.

7. A dispatching system for a microgrid power dispatching method based on blockchain, characterized in that: include: The data acquisition module is used to collect relevant data in the microgrid in real time and upload it to the blockchain network after preprocessing. The relevant data includes power resource data, equipment status data, and user demand data; The data analysis module is used to obtain historical power data and build a power resource prediction model through time series analysis; obtain equipment operating parameters and build an equipment load model through deep learning; obtain historical power consumption data and build a power demand model through machine learning; input relevant data into the power resource prediction model, equipment load model, and power demand model respectively to obtain power resource prediction data, equipment load prediction data, and power demand prediction data respectively; The data processing module is used to extract the data features of historical power data, equipment operating parameters and historical power consumption data, and obtain the features related to power transmission efficiency based on correlation analysis, and determine the respective weights based on principal component analysis; taking maximizing efficiency as the objective function, constructing an efficiency transmission model based on the weights of historical power data, equipment operating parameters and historical power consumption data, and optimizing it through simulated annealing and taboo search to obtain the optimized efficiency transmission model; The scheme processing module is used to input the power resource forecast data, equipment load forecast data, and power demand forecast data into the optimized efficiency transmission model to obtain the power transmission result with maximum efficiency, and then obtain the power dispatch scheme with maximum efficiency.

8. A computer-readable storage medium, characterized in that: The storage medium stores a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1 to 6 is implemented.

9. A computer device, characterized in that: The method comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the method described in any one of claims 1 to 6 is implemented.

Images